[1910.11295] ÚFAL MRPipe at MRP 2019: UDPipe Goes Semantic in the Meaning Representation Parsing Shared Task
The model implicitly learns the linguistic information and the graph structure without the need for any specific hand-crafted or structural knowledge and is suitable for any directed graph, including graphs with cycles
Abstract: We present a system description of our contribution to the CoNLL 2019 shared
task, Cross-Framework Meaning Representation Parsing (MRP 2019). The proposed
architecture is our first attempt towards a semantic parsing extension of the
UDPipe 2.0, a lemmatization, POS tagging and dependency parsing pipeline.
‹Figure 1: Tokenizer pseudocode as a sequence of regular expressions. Expressions with higher number override previous ones. (Methods)›
For the MRP 2019, which features five formally and linguistically different
approaches to meaning representation (DM, PSD, EDS, UCCA and AMR), we propose a
uniform, language and framework agnostic graph-to-graph neural network
architecture. Without any knowledge about the graph structure, and specifically
without any linguistically or framework motivated features, our system
implicitly models the meaning representation graphs.
After fixing a human error (we used earlier incorrect version of provided
test set analyses), our submission would score third in the competition
evaluation. The source code of our system is available at
this https URL.
[1909.02607] Broad-Coverage Semantic Parsing as Transduction1910.01299[1805.11465] AMR Dependency Parsing with a Typed Semantic Algebra[1906.11746] Compositional Semantic Parsing Across Graphbanks[1905.08704] AMR Parsing as Sequence-to-Graph Transduction[1909.00352] Enhancing AMR-to-Text Generation with Dual Graph Representations[1910.10138] Transductive Parsing for Universal Decompositional Semantics[1908.08676] Hierarchically-Refined Label Attention Network for Sequence Labeling[1905.13370] Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning[1907.06142] Tackling Graphical NLP problems with Graph Recurrent Networks